PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
PixArt-α matches commercial text-to-image quality with a diffusion transformer trained in 675 A100 GPU days through decomposed training stages, cross-attention text injection, and vision-language model dense captions.